Ruflo Agentdb
插件 活跃Substrate plugin for Ruflo memory: AgentDB controller bridge (15 agentdb_* MCP tools), RuVector ONNX embeddings (10 embeddings_* tools incl. RaBitQ 32x quantization), and WASM HNSW pattern router (3 ruvllm_hnsw_* tools)
To provide a robust and efficient memory management substrate for Ruflo, enabling advanced features like semantic search, causal knowledge graphs, and memory consolidation.
功能
- AgentDB controller bridge with 15 tools
- RuVector ONNX embeddings with RaBitQ quantization
- WASM-backed HNSW pattern router for up to 11 patterns
- Support for causal knowledge graphs and context synthesis
- Namespacing convention for cross-plugin discoverability
使用场景
- Managing hierarchical and semantic knowledge stores
- Performing large-scale vector searches with memory optimization
- Implementing fast routing for high-priority patterns
- Building and querying causal knowledge graphs
- Integrating AI agent memories across different Ruflo components
非目标
- Providing a user-facing application layer for memory management
- Handling direct user interaction for memory editing (relies on consumer plugins)
- Implementing its own independent vector database; relies on external tooling
- Managing memory across non-Ruflo environments
Documentation
- info:Configuration & parameter referenceWhile parameters are extensively documented in READMEs and tool definitions, default values are not always explicitly stated for all MCP tools.
Trust
- warning:Issues AttentionOpen issues (68) significantly outnumber closed issues (373) in the last 90 days, suggesting slower maintainer response times.
安装
请先添加 Marketplace
/plugin marketplace add ruvnet/ruflo/plugin install ruflo-agentdb@ruflo包含 2 个扩展
Skill (2)
Query AgentDB through the controller bridge -- semantic routing, hierarchical recall, causal graphs, context synthesis, pattern store/search
Vector search via embeddings_* (large-scale HNSW) and ruvllm_hnsw_* (WASM router for ≤11 hot patterns), with RaBitQ 1-bit quantization for 32× memory reduction
质量评分
类似扩展
Ruflo Rag Memory
99RuVector memory with HNSW search, AgentDB, and semantic retrieval
Memory Bridge
100在 Cowork 项目之间共享记忆。停止教 Claude 同样的事情两次。
Si
100Self-Improving Agent: curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills. Provides /si:review, /si:promote, /si:extract, /si:status, and /si:remember slash commands.
Train Sentence Transformers
99Train or fine-tune sentence-transformers models across all three architectures: SentenceTransformer (bi-encoder embeddings), CrossEncoder (rerankers), and SparseEncoder (SPLADE). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing.
Ruflo Market Data
98Market data ingestion — feed normalization, OHLCV vectorization, and HNSW-indexed pattern matching
LLM Application Development
95LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.6 and GPT-5.4